© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40363
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     po
    -0.28
     co
    -0.26
    ä¼ļåıijçĶŁ
    -0.26
    arching
    -0.26
     whole
    -0.25
     vacc
    -0.25
     Bang
    -0.25
    ä¸Ģä¸ĸ
    -0.25
     entirety
    -0.24
    æĬĬèĩªå·±çļĦ
    -0.24
    POSITIVE LOGITS
    amat
    0.26
    å»ī
    0.25
    è¾ĵ
    0.24
    ator
    0.24
    çľĦ
    0.24
    ç©Ĺ
    0.23
     Hulk
    0.23
    ivable
    0.23
    haft
    0.23
    Sir
    0.23
    Activations Density 58.031%

    No Known Activations

    This feature has no known activations.